LWM-Chat-128K-Jax / README.md
wilson1yan's picture
Update README.md
9f67662 verified
|
raw
history blame
1.18 kB
metadata
inference: false


LWM-128K-Jax Model Card

Model details

Model type: LWM-128K-Jax is an open-source model trained from LLaMA-2 on a subset of Books3 filtered data, along with a large collection if image and video data. It is an auto-regressive vision-language model, based on the transformer architecture. These are the Jax / Flax version of the parameters.

Model date: LWM-128K-Jax was trained in January 2024.

Paper or resources for more information: https://largeworldmodel.github.io/

License

Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.

Where to send questions or comments about the model: https://github.com/LargeWorldModel/lwm/issues

Training dataset

  • Books3 dataset
  • 700B text-image pairs from Laion-2B-en, filtered to only keep images with at least 256 resolution
  • 400M text-image pairs from COYO-700M, filtered to only keep images with at least 256 resolution
  • 10M text-video pairs from WebVid10M
  • 3M text-video pairs from a subset of InternVid10M
  • 73K text-video chat pairs from Valley-Instruct-73K
  • 100K text-video chat pairs from Video-ChatGPT